# Releases (remote · mcp.releases.sh)

An agent-friendly API for product changelogs. A unified registry via CLI, API, or MCP.

- Trust score: 75/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.releases.sh`: 75/100 (this document), [markdown](https://verifymcp.io/servers/sh-releases-mcp/mcp.md), [page](https://verifymcp.io/servers/sh-releases-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.releases.sh/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.15.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3988 tokens (~234/item across 17 items; 16 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add --transport http sh-releases-mcp https://mcp.releases.sh/mcp
```

### Codex

```toml
[mcp_servers.sh-releases-mcp]
url = "https://mcp.releases.sh/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sh-releases-mcp": {
      "type": "remote",
      "url": "https://mcp.releases.sh/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sh-releases-mcp --url https://mcp.releases.sh/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sh-releases-mcp:
    url: "https://mcp.releases.sh/mcp"
```

### Other

```json
{
  "mcpServers": {
    "sh-releases-mcp": {
      "type": "http",
      "url": "https://mcp.releases.sh/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 73, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 71, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 68)

First indexed and scored.

## MCP tools (16)

### `search` (~939 tokens)

Search

Unified search across the registry and release content. Returns up to four sections — organizations, catalog entries (products + standalone sources folded into one list), curated collections (cross-org playlists), and releases with CHANGELOG chunks interleaved by relevance.

Use `type` to narrow the surfaces you want and skip the expensive paths. For example, pass `type: ['catalog']` to look up a known entity by name (fast, registry-only); pass `type: ['releases']` when you only care about release content and want to avoid entity lookups. Omit `type` to search all four.

Collections surface via two paths: a direct match on the collection's name/description (lexical in every mode, plus a vector match in hybrid/semantic mode) and a member rollup that includes every collection containing one of the matched orgs. Member rollups carry a list of result-set org slugs that triggered the rollup so a UI can render an "includes X" hint.

Use `entity` (product slug / prod_ id OR source slug / src_ id) to scope release results to one catalog entry. Product identifiers expand to every source under the product. Use `organization` to scope to a whole org. Release retrieval defaults to hybrid (FTS5 + semantic vectors fused via RRF); it silently degrades to lexical when vector infra is unavailable and flags the result.

Input parameters:

- `domain` (string): Scope to the org owning this domain. Input is normalized (scheme/path/www stripped, lowercased), so `https://vercel.com/` and `vercel.com` both work. Falls back to a 'no match' message when the domai…
- `entity` (string): Scope release results to one catalog entry. Accepts a prod_ id (expands to every source under the product), a src_ id, or an org-scoped coordinate in the form orgSlug/slug (e.g. 'vercel/nextjs'). Bar…
- `include_coverage` (boolean): Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.
- `include_empty` (boolean): Include orgs with zero indexed releases in the `orgs` section. Default false — empty orgs are stubs and surface as noise. Scoping by `domain` ignores this and always returns the resolved org.
- `kind` (string): Filter to a specific source/product kind. Release hits resolve through `source.kind ?? product.kind`; catalog hits filter on the row's own kind. The orgs and collections sections are unaffected; chan…
- `limit` (number): Max results per section (default 20)
- `mode` (string): Release-retrieval strategy. 'hybrid' (default) fuses FTS + vector results. 'lexical' is legacy FTS only. 'semantic' is vectors only. Falls back to lexical if vector infra is unavailable.
- `organization` (string): Scope release results to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.
- `product` (string): Scope release results to a specific product's sources. Accepts a prod_ id or an org-scoped coordinate in the form orgSlug/productSlug (e.g. 'vercel/next-js'). Bare slugs without an org prefix are not…
- `query` (string, required): Search query
- `since` (string): Keep only release hits published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are drop…
- `type` (array): Which sections to return. Omit to return all four. Use to skip expensive paths — e.g. ['catalog'] for registry-only lookups, ['releases'] for pure release search, ['collections'] for a quick playlist…
- `until` (string): Keep only release hits published at or before this bound. Same input formats as `since`.

### `get_latest_releases` (~660 tokens)

Get latest releases

Get the most recent releases, optionally filtered by product or organization. Excludes prereleases (canaries / alphas / betas / RCs) by default — pass `include_prereleases: true` to include them.

Cursor-paginated: pass `limit` for slice size (default 10), `cursor` to continue from a prior call. The result's `_meta.pagination` carries `kind: 'cursor'`, `hasMore`, and `nextCursor` when more rows exist; the response text echoes `nextCursor` so an LLM caller can chain without parsing `_meta`. Cursors are stable under inserts — a release added between calls won't shift the slice.

Input parameters:

- `cursor` (string): Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Pass to fetch the next slice. Stale cursors are silently ignored — the call returns a fresh head of the feed.
- `include_coverage` (boolean): Include releases grouped as coverage of another (e.g. marketing posts that re-announce a platform release). Defaults to false so each underlying launch appears once.
- `include_prereleases` (boolean): Include prerelease tags (alphas, betas, RCs, canaries). Defaults to false so the feed matches the public web view.
- `kind` (string): Filter to releases from sources of a specific kind. Resolves through `source.kind ?? product.kind`, so an SDK repo with no own kind still matches its product's kind. Omit to include all kinds.
- `limit` (integer): Slice size (1–200). Defaults to 10.
- `minImportance` (integer): Only include releases with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Releases with no score (unscored) are excluded when this is set. Mirrors the REST `?minImportance…
- `organization` (string): Filter to sources belonging to this organization. Accepts an org_ id, slug, or registered domain.
- `product` (string): Filter to a product's cross-source release feed. Accepts a prod_ id (expands to ALL sources under the product), a src_ id (single source), or an org-scoped coordinate in the form orgSlug/productSlug…
- `since` (string): Keep only releases published at or after this bound. Accepts an ISO date/datetime (`2026-01-01`) or relative shorthand (`90d`, `4w`, `6m`, `2y`). Filters `published_at`; undated releases are dropped.
- `type` (string): Filter by release type: 'feature' for individual releases, 'rollup' for seasonal/quarterly catch-all posts. Omit to include both.
- `until` (string): Keep only releases published at or before this bound. Same input formats as `since`.

### `list_catalog` (~255 tokens)

List catalog

List catalog entries — products and standalone sources combined into one list with an `entryType: 'product' | 'source'` discriminator per row.

Orgs that group multiple sources under a product (e.g. Vercel → Next.js, Turborepo) surface those products; orgs with a single source that isn't part of a product surface it directly as an `entryType: 'source'` entry. Either shape is a reasonable thing to pass to `search(entity: ...)`.

Paginated: defaults to 50 entries per page. Pass `page: 2` for the next slice. The footer surfaces the total when more pages exist.

Input parameters:

- `kind` (string): Filter to catalog entries of a specific kind. Matches each row's own kind (a product's kind, or a standalone source's kind) — no source→product inheritance on this catalog surface. Omit to include al…
- `limit` (integer): Entries per page (1–200). Defaults to 50.
- `organization` (string): Organization to scope to. Accepts an org_ id, slug, domain, or name.
- `page` (integer): 1-based page number. Defaults to 1.

### `get_catalog_entry` (~433 tokens)

Get catalog entry

Detail for a single catalog entry — accepts a prod_ id, src_ id, or an org-scoped coordinate in the form orgSlug/slug (e.g. 'vercel/nextjs' or 'vercel/next-js'). Returns the union of product / source detail fields depending on the entry kind. Source entries list tracked CHANGELOG files by path and byte size. Pass `include_changelog: true` to inline the root CHANGELOG, or `changelog_path` / `changelog_offset` / `changelog_limit` / `changelog_tokens` to embed a specific file or slice — heading-aligned, supports per-package files in monorepos (e.g. `packages/next/CHANGELOG.md`), and emits `totalTokens` / `sliceTokens` for LLM context budgeting. Files over 1MB are flagged as truncated so you know the tail is missing.

Input parameters:

- `changelog_limit` (number): Target slice size in characters. Slice ends at a heading boundary. Defaults to 40000 when slicing without a token budget. Passing this implies include_changelog.
- `changelog_offset` (number): Character offset into the selected CHANGELOG. Snapped forward to the next heading unless 0. Passing this implies include_changelog.
- `changelog_path` (string): Specific CHANGELOG path for a source-kind entry (e.g. 'packages/next/CHANGELOG.md'). Passing this implies include_changelog.
- `changelog_tokens` (number): Target slice size in tokens (cl100k_base). Takes precedence over changelog_limit. Recommended brackets: 2000, 5000, 10000, 20000. Passing this implies include_changelog.
- `identifier` (string, required): Catalog entry identifier: prod_ id, src_ id, or org-scoped coordinate orgSlug/slug (e.g. 'vercel/nextjs'). Bare slugs without an org prefix are not accepted.
- `include_changelog` (boolean): When true, inline the root tracked CHANGELOG for a source-kind entry. Ignored for products.

### `list_organizations` (~231 tokens)

List organizations

List all indexed organizations, optionally filtered. Paginated: defaults to 50 entries per page; pass `page: 2` for the next slice. Orgs with zero indexed releases are hidden by default (curator-stub noise); set `include_empty: true` to see them.

Input parameters:

- `category` (string): Filter to a single category slug (e.g. `ai`, `devops`). Aliases (e.g. `e-commerce`) resolve to their canonical category (`commerce`); unknown values are ignored (unfiltered).
- `include_empty` (boolean): Include orgs with zero indexed releases. Default false — empty orgs are stubs from in-flight discovery or broken parsers and surface as noise on the public catalog.
- `limit` (integer): Entries per page (1–200). Defaults to 50.
- `page` (integer): 1-based page number. Defaults to 1.
- `platform` (string): Filter to orgs with an account on this platform
- `query` (string): Search across org name, slug, domain, and account handles

### `get_organization` (~123 tokens)

Get organization

Get detailed information about a single organization — accounts, tags, sources, products, aliases. When an AI-generated overview exists the response includes a short preview; pass `include_overview: true` to inline the full briefing (with a stale warning if the content is older than 30 days since last write).

Input parameters:

- `identifier` (string, required): Organization identifier. Accepts an org_ id, slug, domain, name, or account handle.
- `include_overview` (boolean): When true, inline the full AI-generated overview instead of the default first-paragraph preview.

### `lookup_domain` (~162 tokens)

Lookup by domain

Resolve a domain to the org or product that owns it. The domain is normalized first (scheme, `www.`, path, and trailing slash stripped, lowercased), so `https://vercel.com/about` and `vercel.com` both look up the same row.

Returns the matching org (with primary-vs-alias distinction) and any products whose alias targets the same domain. Pure resolution — does not probe the domain or materialize anything; unknown domains surface a 'no match' message. Use `lookup_domain` when you have a URL-shaped input; use `get_organization` when you already have a slug or id.

Input parameters:

- `domain` (string, required): Domain to resolve. Any URL-shaped form is accepted; the server normalizes it.

### `list_collections` (~123 tokens)

List collections

List curated collections — named cross-org playlists (e.g. 'Frontier AI Labs') independent of the fixed category taxonomy.

Use `get_collection` for a collection's full member list, or `get_collection_releases` for the interleaved cross-org release feed. Paginated: defaults to 50 entries per page; pass `page: 2` for the next slice.

Input parameters:

- `limit` (integer): Entries per page (1–200). Defaults to 50.
- `page` (integer): 1-based page number. Defaults to 1.

### `get_collection` (~66 tokens)

Get collection

Detail for a single collection — name, description, and the ordered list of member organizations. Hidden / on-demand orgs never leak through; only publicly visible orgs appear in the member list.

Input parameters:

- `slug` (string, required): Collection slug (e.g. 'frontier-ai-labs').

### `get_collection_releases` (~234 tokens)

Get collection releases

Interleaved cross-org release feed for a collection — same shape as `get_latest_releases` but scoped to the collection's member orgs.

Cursor-paginated: pass `limit` for slice size (default 20), `cursor` to continue from a prior call. The result's `_meta.pagination` carries `kind: 'cursor'`, `hasMore`, and `nextCursor` when more rows exist; the response text echoes `nextCursor` so an LLM caller can chain without parsing `_meta`. Cursors are stable under inserts.

Input parameters:

- `cursor` (string): Opaque continuation token from a prior call's `_meta.pagination.nextCursor`. Stale cursors are silently ignored — the call returns a fresh head of the feed.
- `include_prereleases` (boolean): Include prerelease tags (alphas, betas, RCs). Defaults to false so the feed matches the public web view.
- `limit` (integer): Slice size (1–200). Defaults to 20.
- `slug` (string, required): Collection slug (e.g. 'frontier-ai-labs').

### `get_release` (~95 tokens)

Get release

Fetch the full content of a single release by id. Release ids are returned by search or get_latest_releases — pass them here to read the whole entry (e.g. to quote a specific Next.js release note). Accepts the full rel_<nanoid> form or the bare 21-char nanoid.

Input parameters:

- `id` (string, required): Release id — 'rel_<nanoid>' or a bare 21-char nanoid

### `follow` (~141 tokens)

Follow

Follow an organization or a product so it appears in your personalized feed (`get_personalized_feed`). Following an organization implicitly includes all of its products.

Requires a signed-in user (a `relu_` user key or an OAuth token). `entity` is a typed id — an `org_…` id or a `prod_…` id — as returned by `search`, `get_organization`, or `get_catalog_entry`. Idempotent: following something you already follow is a no-op.

Input parameters:

- `entity` (string, required): Entity to follow — an `org_…` or `prod_…` id (from search / get_* results).

### `unfollow` (~80 tokens)

Unfollow

Stop following an organization or product. Requires a signed-in user. `entity` is an `org_…` or `prod_…` id. Idempotent: unfollowing something you don't follow is a no-op.

Input parameters:

- `entity` (string, required): Entity to unfollow — an `org_…` or `prod_…` id.

### `list_follows` (~27 tokens)

List follows

List the organizations and products you follow (newest first). Requires a signed-in user.

### `get_personalized_feed` (~123 tokens)

Get personalized feed

Your personalized release feed — recent releases from the organizations and products you follow, newest first. Requires a signed-in user. Same item shape as `get_latest_releases`, scoped to your follows.

Cursor-paginated: pass `cursor` from a prior response's `_meta.pagination.nextCursor` and optional `limit` (1–100, default 30).

Input parameters:

- `cursor` (string): Opaque cursor from a previous page's `_meta.pagination.nextCursor`.
- `limit` (integer): Entries per page (1–100). Defaults to 30.

### `whats_changed` (~258 tokens)

What's changed

Given a package and a `from`/`to` version, return the changelog entries between them — `(from, to]`, from exclusive, to inclusive — with summaries and breaking-change verdicts. One call instead of reading N changelog pages to plan an upgrade.

\`package` is a tracked source slug or a GitHub `owner/repo` coordinate (set `ecosystem: "github"` for a bare coordinate). Reads already-indexed releases only. If the package isn't in the catalog you'll get a clear 'not tracked' answer (npm/PyPI names may not be mapped to a source yet).

Input parameters:

- `ecosystem` (string): Optional resolution hint; "github" enables matching a bare owner/repo.
- `from` (string, required): Version you're upgrading FROM (exclusive).
- `minImportance` (integer): Only include entries with an AI-scored `importance` >= this value (1-5; 5=landmark, 1=housekeeping). Entries with no score (unscored) are excluded when this is set.
- `package` (string, required): Package identifier — a source slug or a GitHub "owner/repo" coordinate.
- `to` (string, required): Version you're upgrading TO (inclusive).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sh-releases-mcp/mcp#diagnostics

## Score history

- 2026-08-03: 75
- 2026-08-02: 74
- 2026-08-01: 74
- 2026-07-31: 73
- 2026-07-30: 71
- 2026-07-29: 70
- 2026-07-28: 69
- 2026-07-27: 69
- 2026-07-26: 68

## Links

- Remote endpoint: https://mcp.releases.sh/mcp
- Repository: https://github.com/buildinternet/releases
- Changelog RSS feed: https://verifymcp.io/servers/sh-releases-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sh-releases-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sh-releases-mcp/mcp